oush

app.py

@@ -84,16 +84,19 @@ st.write(f"### Accuracy: {round(accuracy * 100, 2)}%")
 joblib.dump(dt, 'heart_disease_dt_model.pkl')
 
 # Convert the model for FHE
+st.write("### Converting the model for FHE...")
 fhe_compatible = FHEDecisionTreeClassifier.from_sklearn_model(dt, x_train, n_bits=10)
 fhe_compatible.compile(x_train)
 
 # Setup the server
+st.write("### Setting up the FHE server...")
 dev = FHEModelDev(path_dir=fhe_directory, model=fhe_compatible)
 dev.save()
 server = FHEModelServer(path_dir=fhe_directory)
 server.load()
 
 # Setup the client
+st.write("### Setting up the FHE client...")
 client = FHEModelClient(path_dir=fhe_directory, key_dir="/tmp/keys_client")
 serialized_evaluation_keys = client.get_serialized_evaluation_keys()
 
@@ -101,13 +104,14 @@ serialized_evaluation_keys = client.get_serialized_evaluation_keys()
 sample_data = clean_data.iloc[0, 1:].values.reshape(1, -1)  # First sample for prediction
 encrypted_data = client.quantize_encrypt_serialize(sample_data)
 
+st.write("### Running the server with encrypted data...")
 # Run the server with encrypted data
 encrypted_result = server.run(encrypted_data, serialized_evaluation_keys)
+st.write("### Decrypting the prediction result...")
 result = client.deserialize_decrypt_dequantize(encrypted_result)
 
-print(result)
 st.write("### Encrypted Prediction Result")
-if result:
-    print("Prediction: The patient is likely to have heart disease.")
+if result == 1:
+    st.write("Prediction: The patient is likely to have heart disease.")
 else:
-    print("Prediction: The patient is unlikely to have heart disease.")
+    st.write("Prediction: The patient is unlikely to have heart disease.")